End-to-end Bridging Resolution on BASHI
43Recognition PrecisionKobayashi et al. (2023)
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Kobayashi et al. (2023)Evaluation Setting=End-to-end2026.05 | 43 | 25.6 | 32.1 | 25.4 | 14.3 | 18.3 | |
| LLMBridgeBackend Model=Gemini-3.1-pro-preview, Evaluation Setting=End-to-end2026.05 | 22.9 | 70 | 34.5 | 14 | 42.8 | 21.1 | |
| LLMBridgeBackend Model=Qwen2.5-7B-Instruct-FT, Evaluation Setting=End-to-end2026.05 | 15.8 | 45.2 | 23.4 | 5 | 14.3 | 7.4 | |
| LLMBridgeBackend Model=Qwen2.5-7B-Instruct, Evaluation Setting=End-to-end2026.05 | 10.5 | 34.9 | 16.1 | 1.1 | 3.6 | 1.6 | |
| LLMBridgeBackend Model=Llama-3.3-70B-Instruct, Evaluation Setting=End-to-end2026.05 | 9.5 | 61.8 | 16.5 | 3.8 | 24.8 | 6.6 |